[Intel-gfx] i915 dma faults on Xen

[Roger Pau Monné]

On Wed, Oct 21, 2020 at 12:33:05PM +0200, Jan Beulich wrote:
> On 21.10.2020 11:58, Roger Pau Monné wrote:
> > On Fri, Oct 16, 2020 at 12:23:22PM -0400, Jason Andryuk wrote:
> >> The RMRRs are:
> >> (XEN) [VT-D]Host address width 39
> >> (XEN) [VT-D]found ACPI_DMAR_DRHD:
> >> (XEN) [VT-D]  dmaru->address = fed90000
> >> (XEN) [VT-D]drhd->address = fed90000 iommu->reg = ffff82c00021d000
> >> (XEN) [VT-D]cap = 1c0000c40660462 ecap = 19e2ff0505e
> >> (XEN) [VT-D] endpoint: 0000:00:02.0
> >> (XEN) [VT-D]found ACPI_DMAR_DRHD:
> >> (XEN) [VT-D]  dmaru->address = fed91000
> >> (XEN) [VT-D]drhd->address = fed91000 iommu->reg = ffff82c00021f000
> >> (XEN) [VT-D]cap = d2008c40660462 ecap = f050da
> >> (XEN) [VT-D] IOAPIC: 0000:00:1e.7
> >> (XEN) [VT-D] MSI HPET: 0000:00:1e.6
> >> (XEN) [VT-D]  flags: INCLUDE_ALL
> >> (XEN) [VT-D]found ACPI_DMAR_RMRR:
> >> (XEN) [VT-D] endpoint: 0000:00:14.0
> >> (XEN) [VT-D]dmar.c:615:   RMRR region: base_addr 78863000 end_addr 78882fff
> >> (XEN) [VT-D]found ACPI_DMAR_RMRR:
> >> (XEN) [VT-D] endpoint: 0000:00:02.0
> >> (XEN) [VT-D]dmar.c:615:   RMRR region: base_addr 7d000000 end_addr 7f7fffff
> >> (XEN) [VT-D]found ACPI_DMAR_RMRR:
> >> (XEN) [VT-D] endpoint: 0000:00:16.7
> >> (XEN) [VT-D]dmar.c:581:  Non-existent device (0000:00:16.7) is
> >> reported in RMRR (78907000, 78986fff)'s scope!
> >> (XEN) [VT-D]dmar.c:596:   Ignore the RMRR (78907000, 78986fff) due to
> > 
> > This is also part of a reserved region, so should be added to the
> > iommu page tables anyway regardless of this message.
> 
> Could you clarify why you think so? RMRRs are tied to devices, so
> if a device in reality doesn't exist (and no other one uses the
> same range), I don't see why an IOMMU mapping would be needed
> (unless to work around some related firmware bug). Plus aiui none
> of the IOMMU faults actually report this range as having got
> accessed.

Since it's the hardware domain that gets the gfx card assigned here it
will get any reserved regions added to the IOMMU page tables in
arch_iommu_hwdom_init. I agree it's not relevant here, since those are
not the regions reported in the IOMMU faults.

Roger.